相关论文: Combining Trigram-based and Feature-based Methods …

Recently, Chinese Spell Checking(CSC), a task to detect erroneous characters in a sentence and correct them, has attracted extensive interest because of its wide applications in various NLP tasks. Most of the existing methods have utilized…

Contextualized word representations are able to give different representations for the same word in different contexts, and they have been shown to be effective in downstream natural language processing tasks, such as question answering,…

Natural image matting separates the foreground from background in fractional occupancy which can be caused by highly transparent objects, complex foreground (e.g., net or tree), and/or objects containing very fine details (e.g., hairs).…

This thesis investigates how the sub-structure of words can be accounted for in probabilistic models of language. Such models play an important role in natural language processing tasks such as translation or speech recognition, but often…

Multilingual speakers often switch between languages to express themselves on social communication platforms. Sometimes, the original script of the language is preserved, while using a common script for all the languages is quite popular as…

Recent work raises concerns about the use of standard splits to compare natural language processing models. We propose a Bayesian statistical model comparison technique which uses k-fold cross-validation across multiple data sets to…

The presence of sarcasm in conversational systems and social media like chatbots, Facebook, Twitter, etc. poses several challenges for downstream NLP tasks. This is attributed to the fact that the intended meaning of a sarcastic text is…

Recently, Large Language Models (LLMs) have demonstrated remarkable advancements in Natural Language Processing (NLP). However, generating high-quality text that balances coherence, diversity, and relevance remains challenging. Traditional…

Phrases are essential to understand the core concepts in conversations. However, due to their rare occurrence in training data, correct translation of phrases is challenging in speech translation tasks. In this paper, we propose a phrase…

Diarization is a crucial component in meeting transcription systems to ease the challenges of speech enhancement and attribute the transcriptions to the correct speaker. Particularly in the presence of overlapping or noisy speech, these…

Over the last years, various sentence embedders have been an integral part in the success of current machine learning approaches to Natural Language Processing (NLP). Unfortunately, multiple sources have shown that the bias, inherent in the…

Rare word recognition can be improved by adapting ASR models to synthetic data that includes these words. Further improvements can be achieved through contextual biasing, which trains and adds a biasing module into the model architecture to…

Lexicase selection is a semantic-aware parent selection method, which assesses individual test cases in a randomly-shuffled data stream. It has demonstrated success in multiple research areas including genetic programming, genetic…

General purpose language models (LMs) encounter difficulties when processing domain-specific jargon and terminology, which are frequently utilized in specialized fields such as medicine or industrial settings. Moreover, they often find it…

In this paper, we reformulated the spell correction problem as a machine translation task under the encoder-decoder framework. This reformulation enabled us to use a single model for solving the problem that is traditionally formulated as…

In this paper we introduce a method to detect words or phrases in a given sequence of alphabets without knowing the lexicon. Our linear time unsupervised algorithm relies entirely on statistical relationships among alphabets in the input…

Language segmentation consists in finding the boundaries where one language ends and another language begins in a text written in more than one language. This is important for all natural language processing tasks. The problem can be solved…

Language Models are extremely susceptible to performance collapse with even small changes to input prompt strings. Libraries such as DSpy (from Stanford NLP) avoid this problem through demonstration-based prompt optimisation. Inspired by…

Since the dawn of the computing era, information has been represented digitally so that it can be processed by electronic computers. Paper books and documents were abundant and widely being published at that time; and hence, there was a…

This paper proposes a method for unsupervised anomalous sound detection (UASD) and captioning the reason for detection. While there is a method that captions the difference between given normal and anomalous sound pairs, it is assumed to be…